DS-HGNN achieves lower RMSE for stress and displacement prediction on stiffened panels than six benchmark GNN models and matches top accuracy with 19-38% fewer training samples.
hub
How Attentive are Graph Attention Networks?
39 Pith papers cite this work, alongside 42 external citations. Polarity classification is still indexing.
39
Pith papers citing it
42
external citations · Pith
abstract
Graph Attention Networks (GATs) are one of the most popular GNN architectures and are considered as the state-of-the-art architecture for representation learning with graphs. In GAT, every node attends to its neighbors given its own representation as the query. However, in this paper we show that GAT computes a very limited kind of attention: the ranking of the attention scores is unconditioned on the query node. We formally define this restricted kind of attention as static attention and distinguish it from a strictly more expressive dynamic attention. Because GATs use a static attention mechanism, there are simple graph problems that GAT cannot express: in a controlled problem, we show that static attention hinders GAT from even fitting the training data. To remove this limitation, we introduce a simple fix by modifying the order of operations and propose GATv2: a dynamic graph attention variant that is strictly more expressive than GAT. We perform an extensive evaluation and show that GATv2 outperforms GAT across 11 OGB and other benchmarks while we match their parametric costs. Our code is available at https://github.com/tech-srl/how_attentive_are_gats . GATv2 is available as part of the PyTorch Geometric library, the Deep Graph Library, and the TensorFlow GNN library.
hub tools
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
Cellina uses supervised disentanglement to separate cell intrinsic states from spatial contexts for counterfactual predictions on tissue graphs, outperforming baselines on 2.5M+ cells from cancer and brain data.
CausalPOI proposes a spatio-temporal graph causal learning method for cold-start POI check-in forecasting that builds functional interaction graphs and treatment-control pairs to outperform baselines on SafeGraph data.
Introduces graph-to-image prediction of per-node dynamic stability landscapes in oscillator networks from topology, releases two 10k-graph datasets, and shows GNN-CNN models achieve good accuracy with cross-size generalization.
MacroDiff+ applies a dual-domain physics-guided geometric diffusion model to macro placement and reports 6.1-6.2% wirelength reduction on ISPD2005 MMS benchmarks with better scalability.
Vibrational mode graphs from molecular dynamics enable sequence-free protein function prediction via graph neural networks, with entrainment improving signals for collective dynamics.
Graphlets mined as structural tokens improve zero-shot inductive and transductive link prediction in knowledge graph foundation models across 51 diverse graphs.
A graph transformer with RL stabilizations is the first to exceed benchmarks for dynamic RMSA, supporting up to 13% more traffic load on networks up to 143 nodes.
EstGraph benchmark evaluates LLMs on estimating properties of very large graphs from random-walk samples that fit in context limits.
Concept Graph Convolutions perform message passing on node concepts to increase interpretability of graph neural networks without losing task performance.
Introduces the first large-scale 3D PET/CT dataset with fine-grained RoI annotations for Vietnamese and a graph-enhanced HiRRA framework that achieves SOTA report generation by modeling RoI dependencies.
PROVFUSION fuses three complementary views of provenance data with lightweight schemes and voting to achieve higher detection accuracy and lower false positives than node- or edge-only baselines on nine benchmarks.
CapBench is a new multi-PDK dataset of post-layout 3D windows with high-fidelity capacitance labels and multiple ML-ready representations, plus baseline results showing CNN accuracy versus GNN speed trade-offs.
SCOT uses Sinkhorn entropic optimal transport to learn explicit soft correspondences between unequal region sets for multi-source cross-city transfer, adding contrastive sharpening and cycle reconstruction for stability and a prototype hub for multi-source alignment.
ID-PaS+ introduces an identity-aware predict-and-search framework for general parametric MIPs that outperforms Gurobi and prior PAS methods on real-world large-scale instances.
GNN-Ceff is the first graph neural network model for post-layout effective capacitance prediction in VLSI circuits, delivering up to 929x speedup over serial state-of-the-art methods with improved accuracy on real benchmarks.
Doloris introduces dual conditional diffusion implicit bridges plus a sparsity masking strategy to model unpaired single-cell perturbation responses and reports state-of-the-art results on public datasets.
Per-node boundary degree alone lifts cascade-based epidemic scenario identification by ~19% on Tennessee and Virginia contact networks, and some scenarios are provably indistinguishable without boundary or edge labels.
Graph Cascades uses contagion diffusion to rewire graphs by promoting reinforced multi-hop node pairs to direct neighbors, improving GNN performance on heterophilic and moderate-degree homophilic graphs under specified conditions.
Conditional Graph Diffusion generates continuous negotiation outcomes with high individual rationality using GATv2 encoders, cross-attention fusion, and inference-time normative guidance gradients.
AlphaTransit pairs MCTS with a learned policy-value network to reach 54.6% and 82.1% service rates on a Bloomington transit benchmark, outperforming plain RL and plain MCTS baselines.
A tri-modal contrastive learning method for EEG-based zero-shot visual decoding reports 54.1% top-1 accuracy on the Things-EEG2 200-way benchmark, outperforming prior baselines of 32.4%.
DeCoR co-optimizes crosswalk placement and signal control via reinforcement learning on a real 750 m urban corridor, reporting 23% faster pedestrian access to crossings and 79%/65% reductions in pedestrian/vehicle wait times versus fixed-time baselines.
RS-GNNs predict random sets over classes using belief functions to jointly produce class probabilities and epistemic uncertainty estimates for graph nodes.
citing papers explorer
-
Physics-Guided Dual-Stream Heterogeneous Graph Neural Network for Predicting Full-Field Structural Response of Stiffened Panels
DS-HGNN achieves lower RMSE for stress and displacement prediction on stiffened panels than six benchmark GNN models and matches top accuracy with 19-38% fewer training samples.
-
Querying Counterfactuals on Tissue Graphs with Supervised Disentanglement
Cellina uses supervised disentanglement to separate cell intrinsic states from spatial contexts for counterfactual predictions on tissue graphs, outperforming baselines on 2.5M+ cells from cancer and brain data.
-
CausalPOI: Spatio-Temporal Graph-Based Causal Modeling for Cold-Start POI Check-in Forecasting
CausalPOI proposes a spatio-temporal graph causal learning method for cold-start POI check-in forecasting that builds functional interaction graphs and treatment-control pairs to outperform baselines on SafeGraph data.
-
Learning Dynamic Stability Landscapes in Synchronization Networks
Introduces graph-to-image prediction of per-node dynamic stability landscapes in oscillator networks from topology, releases two 10k-graph datasets, and shows GNN-CNN models achieve good accuracy with cross-size generalization.
-
Physics-Guided Geometric Diffusion for Macro Placement Generation
MacroDiff+ applies a dual-domain physics-guided geometric diffusion model to macro placement and reports 6.1-6.2% wirelength reduction on ISPD2005 MMS benchmarks with better scalability.
-
Frequency-Space Mechanics: A Sequence and Coordinate-Free Representation for Protein Function Prediction
Vibrational mode graphs from molecular dynamics enable sequence-free protein function prediction via graph neural networks, with entrainment improving signals for collective dynamics.
-
Graphlets as Building Blocks for Structural Vocabulary in Knowledge Graph Foundation Models
Graphlets mined as structural tokens improve zero-shot inductive and transductive link prediction in knowledge graph foundation models across 51 diverse graphs.
-
Graph Transformers and Stabilized Reinforcement Learning for Large-Scale Dynamic Routing Modulation and Spectrum Allocation in Elastic Optical Networks
A graph transformer with RL stabilizations is the first to exceed benchmarks for dynamic RMSA, supporting up to 13% more traffic load on networks up to 143 nodes.
-
Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks
EstGraph benchmark evaluates LLMs on estimating properties of very large graphs from random-walk samples that fit in context limits.
-
Concept Graph Convolutions: Message Passing in the Concept Space
Concept Graph Convolutions perform message passing on node concepts to increase interpretability of graph neural networks without losing task performance.
-
Region-Grounded Report Generation for 3D Medical Imaging: A Fine-Grained Dataset and Graph-Enhanced Framework
Introduces the first large-scale 3D PET/CT dataset with fine-grained RoI annotations for Vietnamese and a graph-enhanced HiRRA framework that achieves SOTA report generation by modeling RoI dependencies.
-
Beyond Nodes vs. Edges: A Multi-View Fusion Framework for Provenance-Based Intrusion Detection
PROVFUSION fuses three complementary views of provenance data with lightweight schemes and voting to achieve higher detection accuracy and lower false positives than node- or edge-only baselines on nine benchmarks.
-
CapBench: A Multi-PDK Dataset for Machine-Learning-Based Post-Layout Capacitance Extraction
CapBench is a new multi-PDK dataset of post-layout 3D windows with high-fidelity capacitance labels and multiple ML-ready representations, plus baseline results showing CNN accuracy versus GNN speed trade-offs.
-
SCOT: Multi-Source Cross-City Transfer with Optimal-Transport Soft-Correspondence Objective
SCOT uses Sinkhorn entropic optimal transport to learn explicit soft correspondences between unequal region sets for multi-source cross-city transfer, adding contrastive sharpening and cycle reconstruction for stability and a prototype hub for multi-source alignment.
-
ID-PaS+ : Identity-Aware Predict-and-Search for General Mixed-Integer Linear Programs
ID-PaS+ introduces an identity-aware predict-and-search framework for general parametric MIPs that outperforms Gurobi and prior PAS methods on real-world large-scale instances.
-
Effective Capacitance Modeling Using Graph Neural Networks
GNN-Ceff is the first graph neural network model for post-layout effective capacitance prediction in VLSI circuits, delivering up to 929x speedup over serial state-of-the-art methods with improved accuracy on real benchmarks.
-
Doloris: Dual Conditional Diffusion Implicit Bridges with Sparsity Masking Strategy for Unpaired Single-Cell Perturbation Estimation
Doloris introduces dual conditional diffusion implicit bridges plus a sparsity masking strategy to model unpaired single-cell perturbation responses and reports state-of-the-art results on public datasets.
-
Boundary Degree as a Node-level Feature for Epidemic Scenario Identification in Agent-based Cascade Simulations
Per-node boundary degree alone lifts cascade-based epidemic scenario identification by ~19% on Tennessee and Virginia contact networks, and some scenarios are provably indistinguishable without boundary or edge labels.
-
Graph Cascades: Contagion-Based Mesoscopic Rewiring for Structure-Aware Graph Machine Learning
Graph Cascades uses contagion diffusion to rewire graphs by promoting reinforced multi-hop node pairs to direct neighbors, improving GNN performance on heterophilic and moderate-degree homophilic graphs under specified conditions.
-
Conditional Graph Diffusion for Negotiation Support: Overcoming Discrete Infeasibility and Preference Elicitation Gaps
Conditional Graph Diffusion generates continuous negotiation outcomes with high individual rationality using GATv2 encoders, cross-attention fusion, and inference-time normative guidance gradients.
-
AlphaTransit: Learning to Design City-scale Transit Routes
AlphaTransit pairs MCTS with a learned policy-value network to reach 54.6% and 82.1% service rates on a Bloomington transit benchmark, outperforming plain RL and plain MCTS baselines.
-
MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding
A tri-modal contrastive learning method for EEG-based zero-shot visual decoding reports 54.1% top-1 accuracy on the Things-EEG2 200-way benchmark, outperforming prior baselines of 32.4%.
-
DeCoR: Design and Control Co-Optimization for Urban Streets Using Reinforcement Learning
DeCoR co-optimizes crosswalk placement and signal control via reinforcement learning on a real 750 m urban corridor, reporting 23% faster pedestrian access to crossings and 79%/65% reductions in pedestrian/vehicle wait times versus fixed-time baselines.
-
Random-Set Graph Neural Networks
RS-GNNs predict random sets over classes using belief functions to jointly produce class probabilities and epistemic uncertainty estimates for graph nodes.
-
GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking
GEM achieves 65.19% joint goal accuracy on MultiWOZ 2.2 by routing between a graph neural network expert for dialogue structure and a T5 expert for sequences, plus ReAct agents for value generation, outperforming prior SOTA methods.
-
SOAR: Real-Time Joint Optimization of Order Allocation and Robot Scheduling in Robotic Mobile Fulfillment Systems
SOAR is a unified DRL method using soft allocations, event-driven MDP, and heterogeneous graph transformers that cuts global makespan by 7.5% and average order completion time by 15.4% at sub-100ms latency in RMFS.
-
Qubit-Scalable CVRP via Lagrangian Knapsack Decomposition and Noise-Aware Quantum Execution
A hybrid quantum framework decomposes CVRP into bounded-width knapsack subproblems, trains a reinforcement learning controller for Lagrangian multipliers, and uses a contextual bandit to adapt quantum hardware execution, yielding improved routing quality on standard test instances.
-
A Structure-Preserving Graph Neural Solver for Parametric Hyperbolic Conservation Laws
A structure-preserving GNN solver for parametric hyperbolic conservation laws achieves superior long-horizon stability and orders-of-magnitude speedups over high-resolution simulations on supersonic flow benchmarks.
-
Learning Ad Hoc Network Dynamics via Graph-Structured World Models
G-RSSM learns per-node dynamics in wireless ad hoc networks via graph attention and trains clustering policies through imagined rollouts, generalizing from N=50 training to larger networks.
-
Energy-Guided Generative Modeling for Low-Energy Molecular Structure Discovery
EnFlow integrates flow-based conformer generation with energy landscape modeling to enable joint ensemble generation and ground-state identification using only 1-2 ODE steps.
-
PINNOCHIO: Physics-Informed Neural Network for Coupled Hyperelastic Interface-Volume Simulation in Orthognathic Surgery
PINNOCHIO applies a hybrid sequential PINN decomposition to coupled hyperelastic interface-volume simulation, outperforming baselines on surface accuracy and speed in a 40-patient cohort while maintaining physical consistency from partial surface supervision.
-
On Efficient Scaling of GNNs via IO-Aware Layers Implementations
IO-aware GPU kernels for SpMM convolutions, degree-aware reductions, and fused attention layers deliver median speedups of 1.6-2.6x (up to 10x) and memory reductions up to 76x over DGL/PyG baselines on realistic graphs.
-
Deep Neural Sheaf Diffusion
DNSD replaces the sheaf Laplacian with a sheaf adjacency operator, adds normalization and gating, and empirically outperforms GNN and NSD baselines by up to 30 percentage points on synthetic long-range graph tasks while also improving on real-world benchmarks.
-
Bridging Data and Physics: A Graph Neural Network-Based Hybrid Twin Framework
A GNN-based hybrid twin learns the ignorance component of physics simulations from sparse data and generalizes corrections across meshes, geometries, and loads in nonlinear heat transfer.
-
A Parametric Multiscale Surrogate Framework Based on Texture-Generalizable Deep Material Networks for Polycrystal Modeling
A single trained TACS-GNN-ODMN framework builds accurate, physics-interpretable surrogate models for unseen polycrystalline microstructures without retraining, predicting stress-strain response (≤2% mean error) and texture evolution at 224-281× speed-up.
-
Latent graph encoding of multimodal neuroimaging features with generative AI architectures
A graph-attention-based multimodal VAE achieves competitive reconstruction and generation of structural and functional MRI features while being more computationally efficient than diffusion-based alternatives.
-
STAGformer: A Spatio-temporal Agent Graph Transformer for Micro Mobility Demand Forecasting
STAGformer forecasts bike-station demand with linear-complexity spatial-temporal agent attention and reports lower RMSE/MAE than listed baselines on NYC and Chicago data.
-
Graph-GSReg: Leveraging 3D Scene Graphs for Gaussian Splatting Registration
Graph-GSReg reformulates 3D Gaussian Splatting registration as a 3D scene graph registration problem and adds self-supervised test-time optimization for consistent merged scenes.
-
Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey
A survey compiling graph rewiring techniques for mitigating over-squashing and over-smoothing in GNNs.